1 citations · 1 across the 6 of their papers we have counts for
7 papers · 1 filter
Improving the Dependency on Fine-Tuning Data in Transfer Learning for Speech Emotion Recognition
Ricardo García, Rodrigo Mahu, Carlos Busso +1
Compensating for train-test mismatches in acoustic environments is important for deployable speech solutions. This paper proposes to reduce the amount of fine-tuning data needed in…
Long Listening Thoughts: Eliciting Open Auditory Reasoning with Deliberative Perception and Cognitive Refinement
Jaeyeon Kim, Chao-Han Huck Yang, Luoyi Zhang +5
We introduce Long Listening Thoughts (LLT), a framework for constructing post-training datasets that improves audio reasoning by pairing deliberate perceptual grounding with explic…
Voice Agents under Acoustic Stress: From Signal Degradation to Interaction and Action
Amir Ivry, Kai-Wei Chang, Lin Zhang +2
Voice agents must complete users' tasks despite noise, reverberation, and competing speech. Evaluating agents' robustness therefore requires following how acoustic conditions affec…
Listen to the Latents: Self-Correcting Speech Recognition in Large Audio Language Models Through Hidden-State Interactions
Chan-Jan Hsu, Jaeyeon Kim, Chao-Han Huck Yang +3
Recent automatic speech recognition (ASR) systems increasingly integrate large language models (LLMs) to leverage their semantic knowledge, either externally through logit fusion o…
AffectCodec: Emotion-Preserving Neural Speech Codec for Expressive Speech Modeling
Jiacheng Shi, Hongfei Du, Xinyuan Song +3
Neural speech codecs provide discrete representations for speech language models, but emotional cues are often degraded during quantization. Existing codecs mainly optimize acousti…
MSP-Conversation: A Corpus for Naturalistic, Time-Continuous Emotion Recognition
Luz Martinez-Lucas, Pravin Mote, Abinay Reddy Naini +2
Affective computing aims to understand and model human emotions for computational systems. Within this field, speech emotion recognition (SER) focuses on predicting emotions convey…
On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation
Chan-Jan Hsu, Liang-Hsuan Tseng, Yi-Cheng Lin +5
Generative spoken language models pretrained on large-scale raw audio can continue a speech prompt with appropriate content while preserving attributes like speaker and emotion, se…